Cover Image

Improving LLM-based Recommendation with Self-Hard Negatives from Intermediate Layers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Bingqian, Zheng, Bowen, Wang, Xiaolei, Zhang, Long, Wang, Jinpeng, Chen, Sheng, Zhao, Wayne Xin, Wen, Ji-rong
Format:	Preprint
Published:	2026
Subjects:	Information Retrieval Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LARES: Latent Reasoning for Sequential Recommendation
by: Liu, Enze, et al.
Published: (2025)

Tapping the Potential of Large Language Models as Recommender Systems: A Comprehensive Framework and Empirical Analysis
by: Xu, Lanling, et al.
Published: (2024)

Deep Research for Recommender Systems
by: Ou, Kesha, et al.
Published: (2026)

Sequence-level Semantic Representation Fusion for Recommender Systems
by: Xu, Lanling, et al.
Published: (2024)

DeepRec: Towards a Deep Dive Into the Item Space with Large Language Model Based Recommendation
by: Zheng, Bowen, et al.
Published: (2025)

Bridging Textual-Collaborative Gap through Semantic Codes for Sequential Recommendation
by: Liu, Enze, et al.
Published: (2025)

Improving Conversational Recommendation Systems via Counterfactual Data Simulation
by: Wang, Xiaolei, et al.
Published: (2023)

Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Models
by: Wang, Xiaolei, et al.
Published: (2023)

Search-Based Interaction For Conversation Recommendation via Generative Reward Model Based Simulated User
by: Wang, Xiaolei, et al.
Published: (2025)

Universal Item Tokenization for Transferable Generative Recommendation
by: Zheng, Bowen, et al.
Published: (2025)

Enhancing Graph Contrastive Learning with Reliable and Informative Augmentation for Recommendation
by: Zheng, Bowen, et al.
Published: (2024)

Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation
by: Zheng, Bowen, et al.
Published: (2023)

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders
by: Shi, Wentao, et al.
Published: (2026)

Pre-training Generative Recommender with Multi-Identifier Item Tokenization
by: Zheng, Bowen, et al.
Published: (2025)

Hard Negative Sampling via Large Language Models for Recommendation
by: Zhao, Chu, et al.
Published: (2025)

Enhancing Sequential Recommender with Large Language Models for Joint Video and Comment Recommendation
by: Zheng, Bowen, et al.
Published: (2024)

Generative Recommender with End-to-End Learnable Item Tokenization
by: Liu, Enze, et al.
Published: (2024)

Action is All You Need: Dual-Flow Generative Ranking Network for Recommendation
by: Guo, Hao, et al.
Published: (2025)

Enhanced Bayesian Personalized Ranking for Robust Hard Negative Sampling in Recommender Systems
by: Shi, Kexin, et al.
Published: (2024)

SyNeg: LLM-Driven Synthetic Hard-Negatives for Dense Retrieval
by: Li, Xiaopeng, et al.
Published: (2024)

Curriculum-scheduled Knowledge Distillation from Multiple Pre-trained Teachers for Multi-domain Sequential Recommendation
by: Sun, Wenqi, et al.
Published: (2024)

Hierarchical Intent-guided Optimization with Pluggable LLM-Driven Semantics for Session-based Recommendation
by: Chen, Jinpeng, et al.
Published: (2025)

GenCI: Generative Modeling of User Interest Shift via Cohort-based Intent Learning for CTR Prediction
by: Ou, Kesha, et al.
Published: (2026)

A Federated Framework for LLM-based Recommendation
by: Zhao, Jujia, et al.
Published: (2024)

Slow Thinking for Sequential Recommendation
by: Zhang, Junjie, et al.
Published: (2025)

Generating Negative Samples for Multi-Modal Recommendation
by: Ji, Yanbiao, et al.
Published: (2025)

LLM4Rerank: LLM-based Auto-Reranking Framework for Recommendations
by: Gao, Jingtong, et al.
Published: (2024)

Improving Conversational Recommendation with Contextual Adaptation of External Recommenders and LLM-based Reranking
by: Li, Chuang, et al.
Published: (2025)

SPRec: Self-Play to Debias LLM-based Recommendation
by: Gao, Chongming, et al.
Published: (2024)

Improved Estimation of Ranks for Learning Item Recommenders with Negative Sampling
by: Subbiah, Anushya, et al.
Published: (2024)

Improve Temporal Awareness of LLMs for Sequential Recommendation
by: Chu, Zhendong, et al.
Published: (2024)

Break the ID-Language Barrier: An Adaption Framework for LLM-based Sequential Recommendation
by: Yu, Xiaohan, et al.
Published: (2024)

SessionRec: Next Session Prediction Paradigm For Generative Sequential Recommendation
by: Huang, Lei, et al.
Published: (2025)

Divergence Meets Consensus: A Multi-Source Negative Sampling Framework for Sequential Recommendation
by: Li, Yuanzi, et al.
Published: (2026)

RA-Rec: An Efficient ID Representation Alignment Framework for LLM-based Recommendation
by: Yu, Xiaohan, et al.
Published: (2024)

Self-Calibrated Listwise Reranking with Large Language Models
by: Ren, Ruiyang, et al.
Published: (2024)

Verifiable Reasoning for LLM-based Generative Recommendation
by: Lin, Xinyu, et al.
Published: (2026)

EXIT: An EXplicit Interest Transfer Framework for Cross-Domain Recommendation
by: Huang, Lei, et al.
Published: (2024)

Does LLM Focus on the Right Words? Mitigating Context Bias in LLM-based Recommenders
by: Wang, Bohao, et al.
Published: (2025)

Adaptive Hardness Negative Sampling for Collaborative Filtering
by: Lai, Riwei, et al.
Published: (2024)